diff --git a/litellm/llms/openai_like/embedding/handler.py b/litellm/llms/openai_like/embedding/handler.py
index ce0860724..84b8405e6 100644
--- a/litellm/llms/openai_like/embedding/handler.py
+++ b/litellm/llms/openai_like/embedding/handler.py
@@ -45,7 +45,10 @@ class OpenAILikeEmbeddingHandler(OpenAILikeBase):
         response = None
         try:
             if client is None or isinstance(client, AsyncHTTPHandler):
-                self.async_client = AsyncHTTPHandler(timeout=timeout)  # type: ignore
+                self.async_client = get_async_httpx_client(
+                    llm_provider=litellm.LlmProviders.OPENAI,
+                    params={"timeout": timeout},
+                )
             else:
                 self.async_client = client
 
diff --git a/litellm/llms/vertex_ai_and_google_ai_studio/gemini_embeddings/batch_embed_content_handler.py b/litellm/llms/vertex_ai_and_google_ai_studio/gemini_embeddings/batch_embed_content_handler.py
index 314e129c2..8e2d1f39a 100644
--- a/litellm/llms/vertex_ai_and_google_ai_studio/gemini_embeddings/batch_embed_content_handler.py
+++ b/litellm/llms/vertex_ai_and_google_ai_studio/gemini_embeddings/batch_embed_content_handler.py
@@ -7,8 +7,13 @@ from typing import Any, List, Literal, Optional, Union
 
 import httpx
 
+import litellm
 from litellm import EmbeddingResponse
-from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler, HTTPHandler
+from litellm.llms.custom_httpx.http_handler import (
+    AsyncHTTPHandler,
+    HTTPHandler,
+    get_async_httpx_client,
+)
 from litellm.types.llms.openai import EmbeddingInput
 from litellm.types.llms.vertex_ai import (
     VertexAIBatchEmbeddingsRequestBody,
@@ -150,7 +155,10 @@ class GoogleBatchEmbeddings(VertexLLM):
             else:
                 _params["timeout"] = httpx.Timeout(timeout=600.0, connect=5.0)
 
-            async_handler: AsyncHTTPHandler = AsyncHTTPHandler(**_params)  # type: ignore
+            async_handler: AsyncHTTPHandler = get_async_httpx_client(
+                llm_provider=litellm.LlmProviders.VERTEX_AI,
+                params={"timeout": timeout},
+            )
         else:
             async_handler = client  # type: ignore